Intel/distilbert-base-uncased-squadv1.1-sparse-80-1X4-block

By Intel · ↓ 8 · ♥ 0 · Updated 2022-11-23

What's in this repo

This page lists the files in Intel/distilbert-base-uncased-squadv1.1-sparse-80-1X4-block, including int8-model.onnx.

1 ONNX models (.onnx files)
13 files, including 6 .json, 2 .bin, 1 .md, 1 .onnx, 1 .yaml, 1 .txt
Last updated 2022-11-23

ONNX files

File	Size	Download
int8-model.onnx	—	Download

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

README

Sparse DISTILBERT model (uncased)

Finetuned model pruned to 1:4 structured sparsity.

Intended Use

The model can be used for inference with sparsity optimization. For further details on the model and its usage will be soon available.

Evaluation Results

We get the following results on the SQuADv1.1 tasks development set:

Task	SQuADv1.1 (F1)
	87.00

Model info

question-answering transformers

transformers pytorch onnx distilbert question-answering license:apache-2.0 endpoints_compatible region:us

↓ 8 ♥ 0

Created: 2022-11-23

Updated: 2022-11-23

View on Hugging Face

Files (13)

.gitattributes

README.md

config.json

eval_predictions.json

eval_results.json

int8-model.onnx ONNX

pytorch_model.bin

sparse_int8_ir/conf.yaml

sparse_int8_ir/model.bin

special_tokens_map.json

tokenizer.json

tokenizer_config.json

vocab.txt